© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49312
    Prev
    Next
    INDEX
    Explanations

    math expressions with sqrt or pi or omega

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    гаÑĤ
    -0.07
    eret
    -0.07
    ijke
    -0.07
    ubo
    -0.07
    tev
    -0.07
    åĩ«
    -0.06
    ç±½
    -0.06
    &p
    -0.06
    åĵī
    -0.06
    åı¹
    -0.06
    POSITIVE LOGITS
    .abs
    0.07
    ebet
    0.07
    _signed
    0.07
    ür
    0.07
    aju
    0.07
    atih
    0.07
    sstr
    0.07
    æĦıå¤ĸçļĦ
    0.07
    æĿ°
    0.07
     abs
    0.07
    Activations Density 0.025%

    No Known Activations